It was a fine time for learning in Pittsburgh. John and Sam mentioned some of my favorites. Here’s a few more worth checking out:<\/p>\n
Online Multitask Learning
\nOfer Dekel, Phil Long, Yoram Singer
\nThis is on my reading list. Definitely an area I’m interested in.<\/p>\n
Maximum Entropy Distribution Estimation with Generalized Regularization
\nMiroslav Dud\u00c3\u0192\u00c2\u00adk, Robert E. Schapire<\/p>\n
Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path Higher Order Learning On Graphs><\/a> by Sameer Agarwal, Kristin Branson, and Serge Belongie, looks to be interesteding. They seem to poo-poo “tensorization” of existing graph algorithms.<\/p>\n Cover Trees for Nearest Neighbor<\/a> (Alina Beygelzimer, Sham Kakade, John Langford) finally seems to have gotten published. It’s an embarrassment to the community that it took this long– and a reminder of how diligent one has to be in ensuring good work gets published. This seems to happen on a regular basis. (See A New View of EM<\/a>.)<\/p>\n
\nAndr\u00c3\u0192\u00c2\u00a1s Antos, Csaba Szepesv\u00c3\u0192\u00c2\u00a1ri, R\u00c3\u0192\u00c2\u00a9mi Munos
\nAgain, on the list to read. I saw Csaba and Remi talk about this and related work at an ICML Workshop on Kernel Reinforcement Learning. The big question in my head is how this compares\/contrasts with existing work in reductions to reinforcement learning.<\/a> Are there advantages\/disadvantages?<\/p>\n